Unsupervised representation learning for speech processing has matured greatly in the last
few years. Work in computer vision and natural language processing has paved the way, but …

In this paper we demonstrate methods for reliable and efficient training of discrete
representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs) …

Recent work on unsupervised speech segmentation has used self-supervised models with
phone and word segmentation modules that are trained jointly. This paper instead revisits …

The success of deep learning comes from its ability to capture the hierarchical structure of
data by learning high-level representations defined in terms of low-level ones. In this paper …

We investigate segmenting and clustering speech into low-bitrate phone-like sequences
without supervision. We specifically constrain pretrained self-supervised vector-quantized …

Typically, unsupervised segmentation of speech into the phone-and wordlike units are
treated as separate tasks and are often done via different methods which do not fully …

We investigate the possibility of forcing a self-supervised model trained using a contrastive
predictive loss to extract slowly varying latent representations. Rather than producing …

We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns
hierarchical discrete representations of the data. By utilizing a novel objective function, each …

Accurate, high-throughput, and unbiased analysis of plutonium oxide particles is necessary
for analysis of the underlying phenomena associated with the process parameters involved …

Historical handwritten documents guard an important part of human knowledge only at the
reach of a few scholars and experts. Recent developments in machine learning have the …